Three-dimensional TV: a novel method for generating surrogate depth maps using colour information

Tam, Wa James; Vázquez, Carlos; Speranza, Filippo

doi:10.1117/12.807147

Cited by 27 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One approach by Tam et al [2] is to simply use the Cr channel of an image in the YCbCr colour space as the depth estimate. The assumption is that the colour information is distributed in such a way that it mimics the actual depth in the image.…”

Section: *Corresponding Authormentioning

confidence: 99%

See 1 more Smart Citation

Semi-automatic synthetic depth map generation for video using random walks

Rzeszutek

Phan

Androutsos

2011

2011 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

We present a method for easily generating depth maps from monoscopic (i.e. "2D") video footage in order to convert them into stereoscopic, or "3D", footage. Our method uses user-defined strokes for a number of keyframes in the original footage and interpolates between the keyframes to provide a sparse labelling for each frame. We then apply the Random Walks algorithm to the footage to provide depth estimates based on the input provided by the user. These depth maps can then be used to generate novel views through depthbased image rendering.Index Terms-random walks, depth maps, 2D-to-3D, stereoscopy, video

show abstract

Section: *Corresponding Authormentioning

confidence: 99%

“…A probabilistic model is finally used to determine the relative depth between patches based on the obtained feature vectors. In these cases, the estimate can either be dependant on the quality of the classifier, as shown in [4], or on the assumption that colour or some other information will approximate depth [2,3].…”

Section: *Corresponding Authormentioning

confidence: 99%

Semi-automatic synthetic depth map generation for video using random walks

Rzeszutek

Phan

Androutsos

2011

2011 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

show abstract

“…Therefore, each unique depth value that a user has provided is assigned an integer label, k ∈ [1,ND], where ND is the total number of unique depths. A binary segmentation is performed for each label separately and the maximum flow values for the graph are recorded.…”

Section: Generating Depth Maps Via Graph Cutsmentioning

confidence: 99%

“…The depth map is ultimately used to generate the stereoscopic image pair. One attempt was made by Tam et al [1] by using the Cr colour channel as the depth map after converting the image into the YCbCr colour space. Another was by Cheng et al [2] using edge information.…”

Section: Introductionmentioning

confidence: 99%

Semi-automatic 2D to 3D image conversion using a hybrid Random Walks and graph cuts based approach

Phan

Rzeszutek

Androutsos

2011

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this paper, we present a semi-automated method for converting conventional 2D images to stereoscopic 3D. User-defined strokes that correspond to a rough estimate of the depth values in the scene are defined for the image of interest. With these strokes, our system thus determines what the depth values are for the rest of the image, producing a depth map that is ultimately used to create a stereoscopic image pair. Our work is based on a similar scheme which employs Random Walks. However, the related work is quite complex, with many processing steps required to produce the final stereoscopic image pair. Combined with the evident shortcomings of the related work, but noting the merits of Random Walks, we propose a system that is a hybrid between Random Walks, and the popular Graph Cuts segmentation paradigm. Both segmentation algorithms are used to generate a final cohesive depth map, thus combining the merits of both frameworks together. The generated results show that we can produce good quality stereoscopic image pairs, while using a much more simplified method in comparison to the related Random Walks scheme.

show abstract

“…Consumer-electronics manufacturers developed different techniques, but they depended on some perfect assumption and failed on more challenging scenes. Over recent years, a number of algorithms are developed to get depth map automatically such as depth from motion [4], defocus or focus [5], [6], Linear perspective, edge [8], color [9]. These methods use a single depth cue to generate depth.…”

mentioning

confidence: 99%

Development of methodology for depth estimation for images and videos

R.M¹,

V.V²

2017

IJET

View full text Add to dashboard Cite

Abstract-Recent experiences with stereoscopic image/video conversion have sharply increased their demand. Although 3D stereoscopic view enhances visual quality compared to 2D, depth information which is required to generate 3D view is unavailable for existing 2D content. Therefore, there is a large requirement to generate depth information. This paper uses a fusion of monocular cues as Motion, Aerial Perspective cue (AP), Linear Perspective cue (LP), and Defocus cue to estimate the depth. The proposed system developed a mechanism to re-estimate depth map if the estimated depth map is inaccurate in a situation such as fast motion, false foreground estimation. This algorithm is tested in different conditions such as the sequence of camera motion and multiple objects, static cameras and stationary background, a highly dynamic foreground, background with less motion and when motion is behind the foreground. The experimental results show that generation of the depth map is very close to the real depth map. Thus, the algorithm can be applied for 2D-to-3D conversion. To evaluate the performance of our system its results are compared with existing algorithms. The subjective evaluation test was performed on proposed algorithm. The result shows that proposed system has good performance.Keyword -Depth Map, 3D Video, 2D-to-3D conversion, Monocular cue, motion cue. I. INTRODUCTION There are numbers of 3D hardware's available such as 3D TVs, Blu-Ray Players, smart phones, Kinect Camera, LASER cameras. The new 3D can be generated by using such devices. In this, two or more than two cameras are fixed at particular angles. Two views (left and right) are generated to get a stereoscopic view. Large number of companies are working in the same field such as Dynamic Digital depth (DDD), HD logicx, Himax Technologies, In-Tree, Legend 3D, Samsung, LG, Stereo D, JVC, IMAX, but not limited. However, researchers are still working on algorithm which gives superior quality of depth estimation. The depth estimation from video or image can be done either by monocular view or by binocular view. The binocular video consists of two view images or two video similar to left view and right view. Thus, the depth can be extracted from left view and right view by comparing different features in two views. The monocular view consists of single image or video. It is necessary to generate a left view and a right view from single view depending on various cues as Color, Aerial Perspective cue, Linear Perspective cue, motion, focus/defocus etc. Thus, the estimation of the depth from a monocular video/image is a difficult task. The conversion of 2D-to-3D video involves two steps: Depth estimation from a given 2D video and generation of two view left view and right view. The task of generation of two views, left view and right view is performed by algorithms known as Depth based image rendering [DIBR]. These algorithms were well understood and there exists an algorithm that produces good quality video. Therefore, there is a requirement to develop a device (e...

show abstract

Three-dimensional TV: a novel method for generating surrogate depth maps using colour information

Cited by 27 publications

References 9 publications

Semi-automatic synthetic depth map generation for video using random walks

Semi-automatic synthetic depth map generation for video using random walks

Semi-automatic 2D to 3D image conversion using a hybrid Random Walks and graph cuts based approach

Development of methodology for depth estimation for images and videos

Contact Info

Product

Resources

About